Unlock instant, AI-driven research and patent intelligence for your innovation.

A Subspace Clustering Method for Multi-view Data Based on Difference and Consistency Constraints

A clustering method and subspace technology, applied in the field of subspace clustering of multi-view data, can solve the problem of not fully utilizing the redundancy and difference information of multi-view data.

Active Publication Date: 2019-12-13
BEIJING UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing multi-view data clustering methods usually only consider the constraints of the difference or consistency of multi-view data information, and do not make full use of the redundancy and difference information of multi-view data.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Subspace Clustering Method for Multi-view Data Based on Difference and Consistency Constraints
  • A Subspace Clustering Method for Multi-view Data Based on Difference and Consistency Constraints
  • A Subspace Clustering Method for Multi-view Data Based on Difference and Consistency Constraints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] Such as figure 1 As shown, the present invention provides a subspace clustering method for multi-view data based on difference and consistency constraints. We add both difference and consistency constraints to the subspace clustering model of multi-view data, and realize the construction of cluster similarity matrix through iteration of a latent matrix variable.

[0064] We use the matrix Represents a given image set (such as face images, handwritten digital images), where each column of the matrix x i A vector representing an image in the image set drawn by row (or column). Then the multi-view form of the image set can use the matrix where v represents the vth view or feature (such as gray value, LBP feature, Gabor feature, etc.) of the image set. The clustering process based on each view of the image is as follows: first, the image set obtains the self-expression coefficient matrix of each view of the image through linear self-representation That is, by solvin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a sub -space clustering method based on differential and consistent constraints, including the following steps: step 1. Different constraints of multi -visual data sub -space cluster; step 2, multi -vision data space space space, multi -vision space space spaceConsistency constraints of clustering; step 3, multi -view sub -space cluster model and solution.Adopt the technical solution of the present invention to make full use of the information of multi -view data to improve the clustering performance of the image.

Description

technical field [0001] The invention belongs to the field of image classification, in particular to a subspace clustering method of multi-view data based on difference and consistency constraints. Background technique [0002] With the development of science and technology, there are more and more ways to obtain data. A large amount of text, image, video and audio data fills all aspects of people's lives. The analysis and processing of large-scale data occupies an increasingly important role in the field of scientific research. more important position. The increasingly complex data content leads to an increase in data dimensions, and many data can be observed from different perspectives or described by multiple features. For example, video surveillance can capture the information of the same place from different angles, and images can be described by different features (such as gray degree value features, texture features, spatial relationship features, etc.). In fact, the...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/23
Inventor 胡永利侯成浩孙艳丰尹宝才
Owner BEIJING UNIV OF TECH